Related papers: Class Incremental Learning for Algorithm Selection
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…
Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…
The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the…
In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information without forgetting old knowledge (i.e., Catastrophic…
Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. Without…
Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i.e., samples). For this purpose,…
We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing anti-forgetting techniques, such as data replay and…
Continual Learning (CL, sometimes also termed incremental learning) is a flavor of machine learning where the usual assumption of stationary data distribution is relaxed or omitted. When naively applying, e.g., DNNs in CL problems, changes…
Imitation learning (IL) is a general learning paradigm for tackling sequential decision-making problems. Interactive imitation learning, where learners can interactively query for expert demonstrations, has been shown to achieve provably…
The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…
With the rapid development of social media, tremendous videos with new classes are generated daily, which raise an urgent demand for video classification methods that can continuously update new classes while maintaining the knowledge of…
Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which…
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic…
Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…
Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world applications and should be learned incrementally. For…
Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In…
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…
Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on optimizing memory storage through coreset selection strategies.…
Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges…
Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…